Update app.py

app.py

@@ -10,10 +10,9 @@ HF_API = os.getenv('HF_API')
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
-if False:
-    # Load the model and tokenizer
-    tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True)
-    model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto",trust_remote_code=True).eval()
+# Load the model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto",trust_remote_code=True).eval()
 
 def generate_summary(prompt):
     # Add instructions to the prompt to signal that you want a summary
@@ -64,7 +63,7 @@ def search_pubmed(query, retmax):
     return pd.DataFrame(article_list)
 
 # Function to summarize articles using Hugging Face's API
-def summarize_with_huggingface(model, selected_articles, USE_LOCAL=False):
+def summarize_with_huggingface(model, selected_articles, USE_LOCAL=True):
     API_URL = f"https://api-inference.huggingface.co/models/{model}"
     # Your Hugging Face API key
     API_KEY = HF_API 
@@ -121,8 +120,8 @@ def summarize_articles(indices, articles_for_display):
 
 PASSWORD = "pass"
 
-def check_password(password):
-    if password == PASSWORD:
+def check_password(username, password):
+    if username == USERNAME and password == PASSWORD:
         return True, "Welcome!"
     else:
         return False, "Incorrect username or password."
@@ -138,32 +137,30 @@ with gr.Blocks() as demo:
         login_button = gr.Button("Login")
         login_result = gr.Textbox(label="Login Result", interactive=False)
 
-#    login_button.click(check_password, inputs=[username_input, password_input], outputs=[login_result])
+    login_button.click(check_password, inputs=[username_input, password_input], outputs=[login_result])
 
-    query_input = gr.Textbox(label="Query Keywords")
     with gr.Row():
-        retmax_input = gr.Slider(minimum=1, maximum=20, value=5, step=1, label="Number of articles")
         model_input = gr.Textbox(label="Enter the model to use", value="h2oai/h2ogpt-4096-llama2-7b-chat")
-    search_button = gr.Button("Search")
-    output_table = gr.Dataframe(headers=["PMID", "Authors", "Title","Abstract" ])
-    summarize_button = gr.Button("Summarize")
-    summary_output = gr.Textbox()
+        query_input = gr.Textbox(label="Query Keywords")
+        retmax_input = gr.Slider(minimum=1, maximum=20, value=5, step=1, label="Number of articles")
+        search_button = gr.Button("Search")
+        output_table = gr.Dataframe(headers=["PMID", "Authors", "Title","Abstract" ])
+        summarize_button = gr.Button("Summarize")
+        summary_output = gr.Textbox()
 
-    model_input.visible = False
-    query_input.visible = False
-    summarize_button.visible = False
+        model_input.visible = False
+        query_input.visible = False
+        summarize_button.visible = False
 
     def process_login(is_success, message):
         if is_success:
             model_input.visible = True
-            query_input.visible = True
+            query_button.visible = True
             summarize_button.visible = True
-        login_result.value = message
+        login_result.update(value=message)
         login_result.visible = True
     
-    login_button.click(check_password, inputs=[password_input], outputs=[login_result]).then(
-        process_login, [login_result], []
-    )
+    login_button.click(check_password, inputs=[username_input, password_input], outputs=[process_login])
 
     def update_output_table(query, retmax):
         df = search_pubmed(query, retmax)
@@ -198,4 +195,4 @@ if False:
             outputs=summary_output
         )
     
-    demo.launch(debug=True)
+    demo.launch(auth=("user", "pass1234"), debug=True)